I think also heavily depends on what you're doing.
If you're in a stable codebase with lots of best practices, patterns, controls (linters, analyzers, etc.), examples already established, then any model will do ~the same plus/minus since there's not much novelty.
If you're building ground up, entirely novel, no reference, I think results will vary with lower capability models.
For me, I do a mix, leaving implementation to Haiku/Luna/DeepSeek and research/feedback/critique to Opus/Sol/Astra/Fable
If you're in a stable codebase with lots of best practices, patterns, controls (linters, analyzers, etc.), examples already established, then any model will do ~the same plus/minus since there's not much novelty.
If you're building ground up, entirely novel, no reference, I think results will vary with lower capability models.
For me, I do a mix, leaving implementation to Haiku/Luna/DeepSeek and research/feedback/critique to Opus/Sol/Astra/Fable